Security checks across malware telemetry and agentic risk
This skill appears to generate product descriptions using clearly described local or HuggingFace AI backends, with no evidence of hidden or destructive behavior.
Prefer the default Ollama backend for private or unreleased product information. Use the HuggingFace backend only when you are comfortable sending the product name and features to HuggingFace-hosted infrastructure, and avoid exposing unrelated secrets in the runtime environment.
"parameters": {"max_new_tokens": 400, "temperature": 0.7, "return_full_text": False},
}
print(f"[HuggingFace] Using model: {model_id}")
resp = requests.post(api_url, headers=headers, json=payload, timeout=60)
if resp.status_code == 503:
print("Model is loading, please retry in ~30 seconds.", file=sys.stderr)
sys.exit(1)67/67 vendors flagged this skill as clean.